An information-driven autonomous robotic explo- ration method on a continuous representation of unknown envi- ronments is proposed in this paper. The approach conveniently handles sparse sensor measurements to build a continuous model of the environment that exploits structural dependencies without the need to resort to a fixed resolution grid map. A gradient field of occupancy probability distribution is regressed from sensor data as a Gaussian process providing frontier boundaries for further exploration. The resulting continuous global frontier surface completely describes unexplored regions and, inherently, provides an automatic stop criterion for a desired sensitivity. The performance of the proposed approach is evaluated through simulation results in the well-known Freiburg and Cave maps. ; Peer Reviewed ; Postprint (author’s final draft)
Exploration on continuous Gaussian process frontier maps
2014-01-01
Sonstige
Elektronische Ressource
Englisch
DDC: | 629 |
BASE | 2018
|Space Exploration: A Frontier for American Collaboration
NTIS | 2008
|Predicting global ionospheric TEC maps using Gaussian process regression
Elsevier | 2023
|